heavy overload forecasting based on RF

  针对使用传统分类器预测配变重过载会因为重过载样本率较低而带来的总正确率很高，重过载预测正确率却很低这一问题，将重抽样与随机森林理论引入分类模型中，构建重抽样-随机森林分类器对配变重过载进行预测。结果表明，新方法在预测配变日重过载类型、重过载开始与结束时间、重过载严重程度方面有较高的准确率。(For the problem of using the traditional classifier to predict the distribution of heavy overload, the total correct rate is high because of the low overload sample rate, and the accuracy of the heavy overload prediction is very low. The resampling and random forest theory are introduced into the classification model. In the construction, the re-sampling-random forest classifier is used to predict the heavy-duty overload. The results show that the new method has higher accuracy in predicting the type of daily variable overload, the start and end time of heavy overload, and the severity of heavy overload.)

基于随机森林理论的配电变压器重过载预测_贺建章.pdf, 483863 , 2019-08-05